© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62785
    Prev
    Next
    INDEX
    Explanations

    left limb injuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç©°
    -0.10
    æľ¬ç«Ļ
    -0.08
    yster
    -0.08
    åIJĦèĩªçļĦ
    -0.08
    Various
    -0.08
    ä¸ĭåįĬåľº
    -0.08
    åħįéĻ¤
    -0.08
    é¢ī
    -0.08
    à¸Ńà¸Ķ
    -0.08
     Paramount
    -0.08
    POSITIVE LOGITS
    most
    0.10
    大åѦæ¯ķä¸ļ
    0.10
    å·¥ç¨ĭè´¨éĩı
    0.10
    人æŃ»äº¡
    0.09
    龸
    0.09
    .pair
    0.09
    åİŁåĽłæĺ¯
    0.09
    åıĪä¸Ģ次
    0.09
    ifest
    0.09
    ä¼ĺçĤ¹
    0.09
    Activations Density 0.036%

    No Known Activations